Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Paolo Bonzini:
 "ARM:

   - Fix unexpected sign extension of KVM_ARM_DEVICE_ID_MASK

   - Tidy-up handling of AArch32 on asymmetric systems

  x86:

   - Fix 'missing ENDBR' BUG for fastop functions

  Generic:

   - Some cleanup and static analyzer patches

   - More fixes to KVM_CREATE_VM unwind paths"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: Drop unnecessary initialization of "ops" in kvm_ioctl_create_device()
  KVM: Drop unnecessary initialization of "npages" in hva_to_pfn_slow()
  x86/kvm: Fix "missing ENDBR" BUG for fastop functions
  x86/kvm: Simplify FOP_SETCC()
  x86/ibt, objtool: Add IBT_NOSEAL()
  KVM: Rename mmu_notifier_* to mmu_invalidate_*
  KVM: Rename KVM_PRIVATE_MEM_SLOTS to KVM_INTERNAL_MEM_SLOTS
  KVM: MIPS: remove unnecessary definition of KVM_PRIVATE_MEM_SLOTS
  KVM: Move coalesced MMIO initialization (back) into kvm_create_vm()
  KVM: Unconditionally get a ref to /dev/kvm module when creating a VM
  KVM: Properly unwind VM creation if creating debugfs fails
  KVM: arm64: Reject 32bit user PSTATE on asymmetric systems
  KVM: arm64: Treat PMCR_EL1.LC as RES1 on asymmetric systems
  KVM: arm64: Fix compile error due to sign extension

arch/arm64/include/asm/kvm_host.h

@@ -929,6 +929,10 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu);
 	(system_supports_mte() &&				\
 	 test_bit(KVM_ARCH_FLAG_MTE_ENABLED, &(kvm)->arch.flags))
 
+#define kvm_supports_32bit_el0()				\
+	(system_supports_32bit_el0() &&				\
+	 !static_branch_unlikely(&arm64_mismatched_32bit_el0))
+
 int kvm_trng_call(struct kvm_vcpu *vcpu);
 #ifdef CONFIG_KVM
 extern phys_addr_t hyp_mem_base;

arch/arm64/include/uapi/asm/kvm.h

@@ -75,9 +75,11 @@ struct kvm_regs {
 
 /* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */
 #define KVM_ARM_DEVICE_TYPE_SHIFT	0
-#define KVM_ARM_DEVICE_TYPE_MASK	(0xffff << KVM_ARM_DEVICE_TYPE_SHIFT)
+#define KVM_ARM_DEVICE_TYPE_MASK	GENMASK(KVM_ARM_DEVICE_TYPE_SHIFT + 15, \
+						KVM_ARM_DEVICE_TYPE_SHIFT)
 #define KVM_ARM_DEVICE_ID_SHIFT		16
-#define KVM_ARM_DEVICE_ID_MASK		(0xffff << KVM_ARM_DEVICE_ID_SHIFT)
+#define KVM_ARM_DEVICE_ID_MASK		GENMASK(KVM_ARM_DEVICE_ID_SHIFT + 15, \
+						KVM_ARM_DEVICE_ID_SHIFT)
 
 /* Supported device IDs */
 #define KVM_ARM_DEVICE_VGIC_V2		0

arch/arm64/kvm/arm.c

@@ -757,8 +757,7 @@ static bool vcpu_mode_is_bad_32bit(struct kvm_vcpu *vcpu)
 	if (likely(!vcpu_mode_is_32bit(vcpu)))
 		return false;
 
-	return !system_supports_32bit_el0() ||
-		static_branch_unlikely(&arm64_mismatched_32bit_el0);
+	return !kvm_supports_32bit_el0();
 }
 
 /**

arch/arm64/kvm/guest.c

@@ -242,7 +242,7 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 		u64 mode = (*(u64 *)valp) & PSR_AA32_MODE_MASK;
 		switch (mode) {
 		case PSR_AA32_MODE_USR:
-			if (!system_supports_32bit_el0())
+			if (!kvm_supports_32bit_el0())
 				return -EINVAL;
 			break;
 		case PSR_AA32_MODE_FIQ:

arch/arm64/kvm/mmu.c

@@ -993,7 +993,7 @@ transparent_hugepage_adjust(struct kvm *kvm, struct kvm_memory_slot *memslot,
 		 * THP doesn't start to split while we are adjusting the
 		 * refcounts.
 		 *
-		 * We are sure this doesn't happen, because mmu_notifier_retry
+		 * We are sure this doesn't happen, because mmu_invalidate_retry
 		 * was successful and we are holding the mmu_lock, so if this
 		 * THP is trying to split, it will be blocked in the mmu
 		 * notifier before touching any of the pages, specifically
@@ -1188,9 +1188,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			return ret;
 	}
 
-	mmu_seq = vcpu->kvm->mmu_notifier_seq;
+	mmu_seq = vcpu->kvm->mmu_invalidate_seq;
 	/*
-	 * Ensure the read of mmu_notifier_seq happens before we call
+	 * Ensure the read of mmu_invalidate_seq happens before we call
 	 * gfn_to_pfn_prot (which calls get_user_pages), so that we don't risk
 	 * the page we just got a reference to gets unmapped before we have a
 	 * chance to grab the mmu_lock, which ensure that if the page gets
@@ -1246,7 +1246,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	else
 		write_lock(&kvm->mmu_lock);
 	pgt = vcpu->arch.hw_mmu->pgt;
-	if (mmu_notifier_retry(kvm, mmu_seq))
+	if (mmu_invalidate_retry(kvm, mmu_seq))
 		goto out_unlock;
 
 	/*

arch/arm64/kvm/sys_regs.c

@@ -652,7 +652,7 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	 */
 	val = ((pmcr & ~ARMV8_PMU_PMCR_MASK)
 	       | (ARMV8_PMU_PMCR_MASK & 0xdecafbad)) & (~ARMV8_PMU_PMCR_E);
-	if (!system_supports_32bit_el0())
+	if (!kvm_supports_32bit_el0())
 		val |= ARMV8_PMU_PMCR_LC;
 	__vcpu_sys_reg(vcpu, r->reg) = val;
 }
@@ -701,7 +701,7 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		val = __vcpu_sys_reg(vcpu, PMCR_EL0);
 		val &= ~ARMV8_PMU_PMCR_MASK;
 		val |= p->regval & ARMV8_PMU_PMCR_MASK;
-		if (!system_supports_32bit_el0())
+		if (!kvm_supports_32bit_el0())
 			val |= ARMV8_PMU_PMCR_LC;
 		__vcpu_sys_reg(vcpu, PMCR_EL0) = val;
 		kvm_pmu_handle_pmcr(vcpu, val);

arch/mips/include/asm/kvm_host.h

@@ -84,8 +84,6 @@
 
 
 #define KVM_MAX_VCPUS		16
-/* memory slots that does not exposed to userspace */
-#define KVM_PRIVATE_MEM_SLOTS	0
 
 #define KVM_HALT_POLL_NS_DEFAULT 500000
 

arch/mips/kvm/mmu.c

@@ -615,17 +615,17 @@ static int kvm_mips_map_page(struct kvm_vcpu *vcpu, unsigned long gpa,
 	 * Used to check for invalidations in progress, of the pfn that is
 	 * returned by pfn_to_pfn_prot below.
 	 */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	/*
-	 * Ensure the read of mmu_notifier_seq isn't reordered with PTE reads in
-	 * gfn_to_pfn_prot() (which calls get_user_pages()), so that we don't
+	 * Ensure the read of mmu_invalidate_seq isn't reordered with PTE reads
+	 * in gfn_to_pfn_prot() (which calls get_user_pages()), so that we don't
 	 * risk the page we get a reference to getting unmapped before we have a
-	 * chance to grab the mmu_lock without mmu_notifier_retry() noticing.
+	 * chance to grab the mmu_lock without mmu_invalidate_retry() noticing.
 	 *
 	 * This smp_rmb() pairs with the effective smp_wmb() of the combination
 	 * of the pte_unmap_unlock() after the PTE is zapped, and the
 	 * spin_lock() in kvm_mmu_notifier_invalidate_<page|range_end>() before
-	 * mmu_notifier_seq is incremented.
+	 * mmu_invalidate_seq is incremented.
 	 */
 	smp_rmb();
 
@@ -638,7 +638,7 @@ static int kvm_mips_map_page(struct kvm_vcpu *vcpu, unsigned long gpa,
 
 	spin_lock(&kvm->mmu_lock);
 	/* Check if an invalidation has taken place since we got pfn */
-	if (mmu_notifier_retry(kvm, mmu_seq)) {
+	if (mmu_invalidate_retry(kvm, mmu_seq)) {
 		/*
 		 * This can happen when mappings are changed asynchronously, but
 		 * also synchronously if a COW is triggered by

arch/powerpc/include/asm/kvm_book3s_64.h

@@ -666,7 +666,7 @@ static inline pte_t *find_kvm_host_pte(struct kvm *kvm, unsigned long mmu_seq,
 	VM_WARN(!spin_is_locked(&kvm->mmu_lock),
 		"%s called with kvm mmu_lock not held \n", __func__);
 
-	if (mmu_notifier_retry(kvm, mmu_seq))
+	if (mmu_invalidate_retry(kvm, mmu_seq))
 		return NULL;
 
 	pte = __find_linux_pte(kvm->mm->pgd, ea, NULL, hshift);

arch/powerpc/kvm/book3s_64_mmu_host.c

@@ -90,7 +90,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
 	unsigned long pfn;
 
 	/* used to check for invalidations in progress */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	/* Get host physical address for gpa */
@@ -151,7 +151,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
 	cpte = kvmppc_mmu_hpte_cache_next(vcpu);
 
 	spin_lock(&kvm->mmu_lock);
-	if (!cpte || mmu_notifier_retry(kvm, mmu_seq)) {
+	if (!cpte || mmu_invalidate_retry(kvm, mmu_seq)) {
 		r = -EAGAIN;
 		goto out_unlock;
 	}

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -578,7 +578,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_vcpu *vcpu,
 		return -EFAULT;
 
 	/* used to check for invalidations in progress */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	ret = -EFAULT;
@@ -693,7 +693,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_vcpu *vcpu,
 
 	/* Check if we might have been invalidated; let the guest retry if so */
 	ret = RESUME_GUEST;
-	if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) {
+	if (mmu_invalidate_retry(vcpu->kvm, mmu_seq)) {
 		unlock_rmap(rmap);
 		goto out_unlock;
 	}

arch/powerpc/kvm/book3s_64_mmu_radix.c

@@ -640,7 +640,7 @@ int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
 	/* Check if we might have been invalidated; let the guest retry if so */
 	spin_lock(&kvm->mmu_lock);
 	ret = -EAGAIN;
-	if (mmu_notifier_retry(kvm, mmu_seq))
+	if (mmu_invalidate_retry(kvm, mmu_seq))
 		goto out_unlock;
 
 	/* Now traverse again under the lock and change the tree */
@@ -830,7 +830,7 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
 	bool large_enable;
 
 	/* used to check for invalidations in progress */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	/*
@@ -1191,7 +1191,7 @@ void kvmppc_radix_flush_memslot(struct kvm *kvm,
 	 * Increase the mmu notifier sequence number to prevent any page
 	 * fault that read the memslot earlier from writing a PTE.
 	 */
-	kvm->mmu_notifier_seq++;
+	kvm->mmu_invalidate_seq++;
 	spin_unlock(&kvm->mmu_lock);
 }
 

arch/powerpc/kvm/book3s_hv_nested.c

@@ -1580,7 +1580,7 @@ static long int __kvmhv_nested_page_fault(struct kvm_vcpu *vcpu,
 	/* 2. Find the host pte for this L1 guest real address */
 
 	/* Used to check for invalidations in progress */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	/* See if can find translation in our partition scoped tables for L1 */

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -219,7 +219,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 	g_ptel = ptel;
 
 	/* used later to detect if we might have been invalidated */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	/* Find the memslot (if any) for this address */
@@ -366,7 +366,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 			rmap = real_vmalloc_addr(rmap);
 		lock_rmap(rmap);
 		/* Check for pending invalidations under the rmap chain lock */
-		if (mmu_notifier_retry(kvm, mmu_seq)) {
+		if (mmu_invalidate_retry(kvm, mmu_seq)) {
 			/* inval in progress, write a non-present HPTE */
 			pteh |= HPTE_V_ABSENT;
 			pteh &= ~HPTE_V_VALID;
@@ -932,7 +932,7 @@ static long kvmppc_do_h_page_init_zero(struct kvm_vcpu *vcpu,
 	int i;
 
 	/* Used later to detect if we might have been invalidated */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	arch_spin_lock(&kvm->mmu_lock.rlock.raw_lock);
@@ -960,7 +960,7 @@ static long kvmppc_do_h_page_init_copy(struct kvm_vcpu *vcpu,
 	long ret = H_SUCCESS;
 
 	/* Used later to detect if we might have been invalidated */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	arch_spin_lock(&kvm->mmu_lock.rlock.raw_lock);

arch/powerpc/kvm/e500_mmu_host.c

@@ -339,7 +339,7 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	unsigned long flags;
 
 	/* used to check for invalidations in progress */
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	/*
@@ -460,7 +460,7 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	}
 
 	spin_lock(&kvm->mmu_lock);
-	if (mmu_notifier_retry(kvm, mmu_seq)) {
+	if (mmu_invalidate_retry(kvm, mmu_seq)) {
 		ret = -EAGAIN;
 		goto out;
 	}

arch/riscv/kvm/mmu.c

@@ -666,7 +666,7 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu,
 		return ret;
 	}
 
-	mmu_seq = kvm->mmu_notifier_seq;
+	mmu_seq = kvm->mmu_invalidate_seq;
 
 	hfn = gfn_to_pfn_prot(kvm, gfn, is_write, &writable);
 	if (hfn == KVM_PFN_ERR_HWPOISON) {
@@ -686,7 +686,7 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu,
 
 	spin_lock(&kvm->mmu_lock);
 
-	if (mmu_notifier_retry(kvm, mmu_seq))
+	if (mmu_invalidate_retry(kvm, mmu_seq))
 		goto out_unlock;
 
 	if (writable) {

arch/x86/include/asm/ibt.h

@@ -31,6 +31,16 @@
 
 #define __noendbr	__attribute__((nocf_check))
 
+/*
+ * Create a dummy function pointer reference to prevent objtool from marking
+ * the function as needing to be "sealed" (i.e. ENDBR converted to NOP by
+ * apply_ibt_endbr()).
+ */
+#define IBT_NOSEAL(fname)				\
+	".pushsection .discard.ibt_endbr_noseal\n\t"	\
+	_ASM_PTR fname "\n\t"				\
+	".popsection\n\t"
+
 static inline __attribute_const__ u32 gen_endbr(void)
 {
 	u32 endbr;
@@ -84,6 +94,7 @@ extern __noendbr void ibt_restore(u64 save);
 #ifndef __ASSEMBLY__
 
 #define ASM_ENDBR
+#define IBT_NOSEAL(name)
 
 #define __noendbr
 

arch/x86/include/asm/kvm_host.h

@@ -53,7 +53,7 @@
 #define KVM_MAX_VCPU_IDS (KVM_MAX_VCPUS * KVM_VCPU_ID_RATIO)
 
 /* memory slots that are not exposed to userspace */
-#define KVM_PRIVATE_MEM_SLOTS 3
+#define KVM_INTERNAL_MEM_SLOTS 3
 
 #define KVM_HALT_POLL_NS_DEFAULT 200000
 

arch/x86/kvm/emulate.c

@@ -326,7 +326,8 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
 	".align " __stringify(FASTOP_SIZE) " \n\t" \
 	".type " name ", @function \n\t" \
 	name ":\n\t" \
-	ASM_ENDBR
+	ASM_ENDBR \
+	IBT_NOSEAL(name)
 
 #define FOP_FUNC(name) \
 	__FOP_FUNC(#name)
@@ -446,27 +447,12 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop);
 	FOP_END
 
 /* Special case for SETcc - 1 instruction per cc */
-
-/*
- * Depending on .config the SETcc functions look like:
- *
- * ENDBR			[4 bytes; CONFIG_X86_KERNEL_IBT]
- * SETcc %al			[3 bytes]
- * RET | JMP __x86_return_thunk	[1,5 bytes; CONFIG_RETHUNK]
- * INT3				[1 byte; CONFIG_SLS]
- */
-#define SETCC_ALIGN	16
-
 #define FOP_SETCC(op) \
-	".align " __stringify(SETCC_ALIGN) " \n\t" \
-	".type " #op ", @function \n\t" \
-	#op ": \n\t" \
-	ASM_ENDBR \
+	FOP_FUNC(op) \
 	#op " %al \n\t" \
-	__FOP_RET(#op) \
-	".skip " __stringify(SETCC_ALIGN) " - (.-" #op "), 0xcc \n\t"
+	FOP_RET(op)
 
-__FOP_START(setcc, SETCC_ALIGN)
+FOP_START(setcc)
 FOP_SETCC(seto)
 FOP_SETCC(setno)
 FOP_SETCC(setc)
@@ -1079,7 +1065,7 @@ static int em_bsr_c(struct x86_emulate_ctxt *ctxt)
 static __always_inline u8 test_cc(unsigned int condition, unsigned long flags)
 {
 	u8 rc;
-	void (*fop)(void) = (void *)em_setcc + SETCC_ALIGN * (condition & 0xf);
+	void (*fop)(void) = (void *)em_setcc + FASTOP_SIZE * (condition & 0xf);
 
 	flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF;
 	asm("push %[flags]; popf; " CALL_NOSPEC

arch/x86/kvm/mmu/mmu.c

@@ -2914,7 +2914,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
 	 * If addresses are being invalidated, skip prefetching to avoid
 	 * accidentally prefetching those addresses.
 	 */
-	if (unlikely(vcpu->kvm->mmu_notifier_count))
+	if (unlikely(vcpu->kvm->mmu_invalidate_in_progress))
 		return;
 
 	__direct_pte_prefetch(vcpu, sp, sptep);
@@ -2928,7 +2928,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
  *
  * There are several ways to safely use this helper:
  *
- * - Check mmu_notifier_retry_hva() after grabbing the mapping level, before
+ * - Check mmu_invalidate_retry_hva() after grabbing the mapping level, before
  *   consuming it.  In this case, mmu_lock doesn't need to be held during the
  *   lookup, but it does need to be held while checking the MMU notifier.
  *
@@ -3056,7 +3056,7 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 		return;
 
 	/*
-	 * mmu_notifier_retry() was successful and mmu_lock is held, so
+	 * mmu_invalidate_retry() was successful and mmu_lock is held, so
 	 * the pmd can't be split from under us.
 	 */
 	fault->goal_level = fault->req_level;
@@ -4203,7 +4203,7 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu,
 		return true;
 
 	return fault->slot &&
-	       mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva);
+	       mmu_invalidate_retry_hva(vcpu->kvm, mmu_seq, fault->hva);
 }
 
 static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
@@ -4227,7 +4227,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	if (r)
 		return r;
 
-	mmu_seq = vcpu->kvm->mmu_notifier_seq;
+	mmu_seq = vcpu->kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	r = kvm_faultin_pfn(vcpu, fault);
@@ -6055,7 +6055,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 
 	write_lock(&kvm->mmu_lock);
 
-	kvm_inc_notifier_count(kvm, gfn_start, gfn_end);
+	kvm_mmu_invalidate_begin(kvm, gfn_start, gfn_end);
 
 	flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end);
 
@@ -6069,7 +6069,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 		kvm_flush_remote_tlbs_with_address(kvm, gfn_start,
 						   gfn_end - gfn_start);
 
-	kvm_dec_notifier_count(kvm, gfn_start, gfn_end);
+	kvm_mmu_invalidate_end(kvm, gfn_start, gfn_end);
 
 	write_unlock(&kvm->mmu_lock);
 }

arch/x86/kvm/mmu/paging_tmpl.h

@@ -589,7 +589,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
 	 * If addresses are being invalidated, skip prefetching to avoid
 	 * accidentally prefetching those addresses.
 	 */
-	if (unlikely(vcpu->kvm->mmu_notifier_count))
+	if (unlikely(vcpu->kvm->mmu_invalidate_in_progress))
 		return;
 
 	if (sp->role.direct)
@@ -838,7 +838,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	else
 		fault->max_level = walker.level;
 
-	mmu_seq = vcpu->kvm->mmu_notifier_seq;
+	mmu_seq = vcpu->kvm->mmu_invalidate_seq;
 	smp_rmb();
 
 	r = kvm_faultin_pfn(vcpu, fault);

include/linux/kvm_host.h

@@ -656,12 +656,12 @@ struct kvm_irq_routing_table {
 };
 #endif
 
-#ifndef KVM_PRIVATE_MEM_SLOTS
-#define KVM_PRIVATE_MEM_SLOTS 0
+#ifndef KVM_INTERNAL_MEM_SLOTS
+#define KVM_INTERNAL_MEM_SLOTS 0
 #endif
 
 #define KVM_MEM_SLOTS_NUM SHRT_MAX
-#define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_PRIVATE_MEM_SLOTS)
+#define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_INTERNAL_MEM_SLOTS)
 
 #ifndef __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
 static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
@@ -765,10 +765,10 @@ struct kvm {
 
 #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
 	struct mmu_notifier mmu_notifier;
-	unsigned long mmu_notifier_seq;
-	long mmu_notifier_count;
-	unsigned long mmu_notifier_range_start;
-	unsigned long mmu_notifier_range_end;
+	unsigned long mmu_invalidate_seq;
+	long mmu_invalidate_in_progress;
+	unsigned long mmu_invalidate_range_start;
+	unsigned long mmu_invalidate_range_end;
 #endif
 	struct list_head devices;
 	u64 manual_dirty_log_protect;
@@ -1357,10 +1357,10 @@ void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc);
 void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
 #endif
 
-void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start,
-				   unsigned long end);
-void kvm_dec_notifier_count(struct kvm *kvm, unsigned long start,
-				   unsigned long end);
+void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
+			      unsigned long end);
+void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
+			    unsigned long end);
 
 long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
@@ -1907,42 +1907,44 @@ extern const struct kvm_stats_header kvm_vcpu_stats_header;
 extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[];
 
 #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
-static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq)
+static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq)
 {
-	if (unlikely(kvm->mmu_notifier_count))
+	if (unlikely(kvm->mmu_invalidate_in_progress))
 		return 1;
 	/*
-	 * Ensure the read of mmu_notifier_count happens before the read
-	 * of mmu_notifier_seq.  This interacts with the smp_wmb() in
-	 * mmu_notifier_invalidate_range_end to make sure that the caller
-	 * either sees the old (non-zero) value of mmu_notifier_count or
-	 * the new (incremented) value of mmu_notifier_seq.
-	 * PowerPC Book3s HV KVM calls this under a per-page lock
-	 * rather than under kvm->mmu_lock, for scalability, so
-	 * can't rely on kvm->mmu_lock to keep things ordered.
+	 * Ensure the read of mmu_invalidate_in_progress happens before
+	 * the read of mmu_invalidate_seq.  This interacts with the
+	 * smp_wmb() in mmu_notifier_invalidate_range_end to make sure
+	 * that the caller either sees the old (non-zero) value of
+	 * mmu_invalidate_in_progress or the new (incremented) value of
+	 * mmu_invalidate_seq.
+	 *
+	 * PowerPC Book3s HV KVM calls this under a per-page lock rather
+	 * than under kvm->mmu_lock, for scalability, so can't rely on
+	 * kvm->mmu_lock to keep things ordered.
 	 */
 	smp_rmb();
-	if (kvm->mmu_notifier_seq != mmu_seq)
+	if (kvm->mmu_invalidate_seq != mmu_seq)
 		return 1;
 	return 0;
 }
 
-static inline int mmu_notifier_retry_hva(struct kvm *kvm,
-					 unsigned long mmu_seq,
-					 unsigned long hva)
+static inline int mmu_invalidate_retry_hva(struct kvm *kvm,
+					   unsigned long mmu_seq,
+					   unsigned long hva)
 {
 	lockdep_assert_held(&kvm->mmu_lock);
 	/*
-	 * If mmu_notifier_count is non-zero, then the range maintained by
-	 * kvm_mmu_notifier_invalidate_range_start contains all addresses that
-	 * might be being invalidated. Note that it may include some false
+	 * If mmu_invalidate_in_progress is non-zero, then the range maintained
+	 * by kvm_mmu_notifier_invalidate_range_start contains all addresses
+	 * that might be being invalidated. Note that it may include some false
 	 * positives, due to shortcuts when handing concurrent invalidations.
 	 */
-	if (unlikely(kvm->mmu_notifier_count) &&
-	    hva >= kvm->mmu_notifier_range_start &&
-	    hva < kvm->mmu_notifier_range_end)
+	if (unlikely(kvm->mmu_invalidate_in_progress) &&
+	    hva >= kvm->mmu_invalidate_range_start &&
+	    hva < kvm->mmu_invalidate_range_end)
 		return 1;
-	if (kvm->mmu_notifier_seq != mmu_seq)
+	if (kvm->mmu_invalidate_seq != mmu_seq)
 		return 1;
 	return 0;
 }

tools/objtool/check.c

@@ -4096,7 +4096,8 @@ static int validate_ibt(struct objtool_file *file)
 		 * These sections can reference text addresses, but not with
 		 * the intent to indirect branch to them.
 		 */
-		if (!strncmp(sec->name, ".discard", 8)			||
+		if ((!strncmp(sec->name, ".discard", 8) &&
+		     strcmp(sec->name, ".discard.ibt_endbr_noseal"))	||
 		    !strncmp(sec->name, ".debug", 6)			||
 		    !strcmp(sec->name, ".altinstructions")		||
 		    !strcmp(sec->name, ".ibt_endbr_seal")		||

virt/kvm/kvm_main.c

@@ -702,30 +702,31 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
 
 	/*
 	 * .change_pte() must be surrounded by .invalidate_range_{start,end}().
-	 * If mmu_notifier_count is zero, then no in-progress invalidations,
-	 * including this one, found a relevant memslot at start(); rechecking
-	 * memslots here is unnecessary.  Note, a false positive (count elevated
-	 * by a different invalidation) is sub-optimal but functionally ok.
+	 * If mmu_invalidate_in_progress is zero, then no in-progress
+	 * invalidations, including this one, found a relevant memslot at
+	 * start(); rechecking memslots here is unnecessary.  Note, a false
+	 * positive (count elevated by a different invalidation) is sub-optimal
+	 * but functionally ok.
 	 */
 	WARN_ON_ONCE(!READ_ONCE(kvm->mn_active_invalidate_count));
-	if (!READ_ONCE(kvm->mmu_notifier_count))
+	if (!READ_ONCE(kvm->mmu_invalidate_in_progress))
 		return;
 
 	kvm_handle_hva_range(mn, address, address + 1, pte, kvm_set_spte_gfn);
 }
 
-void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start,
-				   unsigned long end)
+void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
+			      unsigned long end)
 {
 	/*
 	 * The count increase must become visible at unlock time as no
 	 * spte can be established without taking the mmu_lock and
 	 * count is also read inside the mmu_lock critical section.
 	 */
-	kvm->mmu_notifier_count++;
-	if (likely(kvm->mmu_notifier_count == 1)) {
-		kvm->mmu_notifier_range_start = start;
-		kvm->mmu_notifier_range_end = end;
+	kvm->mmu_invalidate_in_progress++;
+	if (likely(kvm->mmu_invalidate_in_progress == 1)) {
+		kvm->mmu_invalidate_range_start = start;
+		kvm->mmu_invalidate_range_end = end;
 	} else {
 		/*
 		 * Fully tracking multiple concurrent ranges has diminishing
@@ -736,10 +737,10 @@ void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start,
 		 * accumulate and persist until all outstanding invalidates
 		 * complete.
 		 */
-		kvm->mmu_notifier_range_start =
-			min(kvm->mmu_notifier_range_start, start);
-		kvm->mmu_notifier_range_end =
-			max(kvm->mmu_notifier_range_end, end);
+		kvm->mmu_invalidate_range_start =
+			min(kvm->mmu_invalidate_range_start, start);
+		kvm->mmu_invalidate_range_end =
+			max(kvm->mmu_invalidate_range_end, end);
 	}
 }
 
@@ -752,7 +753,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 		.end		= range->end,
 		.pte		= __pte(0),
 		.handler	= kvm_unmap_gfn_range,
-		.on_lock	= kvm_inc_notifier_count,
+		.on_lock	= kvm_mmu_invalidate_begin,
 		.on_unlock	= kvm_arch_guest_memory_reclaimed,
 		.flush_on_ret	= true,
 		.may_block	= mmu_notifier_range_blockable(range),
@@ -763,7 +764,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	/*
 	 * Prevent memslot modification between range_start() and range_end()
 	 * so that conditionally locking provides the same result in both
-	 * functions.  Without that guarantee, the mmu_notifier_count
+	 * functions.  Without that guarantee, the mmu_invalidate_in_progress
 	 * adjustments will be imbalanced.
 	 *
 	 * Pairs with the decrement in range_end().
@@ -779,7 +780,8 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	 * any given time, and the caches themselves can check for hva overlap,
 	 * i.e. don't need to rely on memslot overlap checks for performance.
 	 * Because this runs without holding mmu_lock, the pfn caches must use
-	 * mn_active_invalidate_count (see above) instead of mmu_notifier_count.
+	 * mn_active_invalidate_count (see above) instead of
+	 * mmu_invalidate_in_progress.
 	 */
 	gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end,
 					  hva_range.may_block);
@@ -789,22 +791,22 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	return 0;
 }
 
-void kvm_dec_notifier_count(struct kvm *kvm, unsigned long start,
-				   unsigned long end)
+void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
+			    unsigned long end)
 {
 	/*
 	 * This sequence increase will notify the kvm page fault that
 	 * the page that is going to be mapped in the spte could have
 	 * been freed.
 	 */
-	kvm->mmu_notifier_seq++;
+	kvm->mmu_invalidate_seq++;
 	smp_wmb();
 	/*
 	 * The above sequence increase must be visible before the
 	 * below count decrease, which is ensured by the smp_wmb above
-	 * in conjunction with the smp_rmb in mmu_notifier_retry().
+	 * in conjunction with the smp_rmb in mmu_invalidate_retry().
 	 */
-	kvm->mmu_notifier_count--;
+	kvm->mmu_invalidate_in_progress--;
 }
 
 static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
@@ -816,7 +818,7 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 		.end		= range->end,
 		.pte		= __pte(0),
 		.handler	= (void *)kvm_null_fn,
-		.on_lock	= kvm_dec_notifier_count,
+		.on_lock	= kvm_mmu_invalidate_end,
 		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= false,
 		.may_block	= mmu_notifier_range_blockable(range),
@@ -837,7 +839,7 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 	if (wake)
 		rcuwait_wake_up(&kvm->mn_memslots_update_rcuwait);
 
-	BUG_ON(kvm->mmu_notifier_count < 0);
+	BUG_ON(kvm->mmu_invalidate_in_progress < 0);
 }
 
 static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
@@ -1134,6 +1136,9 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	if (!kvm)
 		return ERR_PTR(-ENOMEM);
 
+	/* KVM is pinned via open("/dev/kvm"), the fd passed to this ioctl(). */
+	__module_get(kvm_chardev_ops.owner);
+
 	KVM_MMU_LOCK_INIT(kvm);
 	mmgrab(current->mm);
 	kvm->mm = current->mm;
@@ -1211,9 +1216,17 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	if (r)
 		goto out_err_no_mmu_notifier;
 
+	r = kvm_coalesced_mmio_init(kvm);
+	if (r < 0)
+		goto out_no_coalesced_mmio;
+
+	r = kvm_create_vm_debugfs(kvm, fdname);
+	if (r)
+		goto out_err_no_debugfs;
+
 	r = kvm_arch_post_init_vm(kvm);
 	if (r)
-		goto out_err_mmu_notifier;
+		goto out_err;
 
 	mutex_lock(&kvm_lock);
 	list_add(&kvm->vm_list, &vm_list);
@@ -1222,25 +1235,13 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	preempt_notifier_inc();
 	kvm_init_pm_notifier(kvm);
 
-	/*
-	 * When the fd passed to this ioctl() is opened it pins the module,
-	 * but try_module_get() also prevents getting a reference if the module
-	 * is in MODULE_STATE_GOING (e.g. if someone ran "rmmod --wait").
-	 */
-	if (!try_module_get(kvm_chardev_ops.owner)) {
-		r = -ENODEV;
-		goto out_err_mmu_notifier;
-	}
-
-	r = kvm_create_vm_debugfs(kvm, fdname);
-	if (r)
-		goto out_err;
-
 	return kvm;
 
 out_err:
-	module_put(kvm_chardev_ops.owner);
-out_err_mmu_notifier:
+	kvm_destroy_vm_debugfs(kvm);
+out_err_no_debugfs:
+	kvm_coalesced_mmio_free(kvm);
+out_no_coalesced_mmio:
 #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
 	if (kvm->mmu_notifier.ops)
 		mmu_notifier_unregister(&kvm->mmu_notifier, current->mm);
@@ -1259,6 +1260,7 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 out_err_no_srcu:
 	kvm_arch_free_vm(kvm);
 	mmdrop(current->mm);
+	module_put(kvm_chardev_ops.owner);
 	return ERR_PTR(r);
 }
 
@@ -2516,7 +2518,7 @@ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
 {
 	unsigned int flags = FOLL_HWPOISON;
 	struct page *page;
-	int npages = 0;
+	int npages;
 
 	might_sleep();
 
@@ -4378,7 +4380,7 @@ void kvm_unregister_device_ops(u32 type)
 static int kvm_ioctl_create_device(struct kvm *kvm,
 				   struct kvm_create_device *cd)
 {
-	const struct kvm_device_ops *ops = NULL;
+	const struct kvm_device_ops *ops;
 	struct kvm_device *dev;
 	bool test = cd->flags & KVM_CREATE_DEVICE_TEST;
 	int type;
@@ -4913,11 +4915,6 @@ static int kvm_dev_ioctl_create_vm(unsigned long type)
 		goto put_fd;
 	}
 
-#ifdef CONFIG_KVM_MMIO
-	r = kvm_coalesced_mmio_init(kvm);
-	if (r < 0)
-		goto put_kvm;
-#endif
 	file = anon_inode_getfile("kvm-vm", &kvm_vm_fops, kvm, O_RDWR);
 	if (IS_ERR(file)) {
 		r = PTR_ERR(file);

virt/kvm/pfncache.c

@@ -112,27 +112,28 @@ static inline bool mmu_notifier_retry_cache(struct kvm *kvm, unsigned long mmu_s
 {
 	/*
 	 * mn_active_invalidate_count acts for all intents and purposes
-	 * like mmu_notifier_count here; but the latter cannot be used
-	 * here because the invalidation of caches in the mmu_notifier
-	 * event occurs _before_ mmu_notifier_count is elevated.
+	 * like mmu_invalidate_in_progress here; but the latter cannot
+	 * be used here because the invalidation of caches in the
+	 * mmu_notifier event occurs _before_ mmu_invalidate_in_progress
+	 * is elevated.
 	 *
 	 * Note, it does not matter that mn_active_invalidate_count
 	 * is not protected by gpc->lock.  It is guaranteed to
 	 * be elevated before the mmu_notifier acquires gpc->lock, and
-	 * isn't dropped until after mmu_notifier_seq is updated.
+	 * isn't dropped until after mmu_invalidate_seq is updated.
 	 */
 	if (kvm->mn_active_invalidate_count)
 		return true;
 
 	/*
 	 * Ensure mn_active_invalidate_count is read before
-	 * mmu_notifier_seq.  This pairs with the smp_wmb() in
+	 * mmu_invalidate_seq.  This pairs with the smp_wmb() in
 	 * mmu_notifier_invalidate_range_end() to guarantee either the
 	 * old (non-zero) value of mn_active_invalidate_count or the
-	 * new (incremented) value of mmu_notifier_seq is observed.
+	 * new (incremented) value of mmu_invalidate_seq is observed.
 	 */
 	smp_rmb();
-	return kvm->mmu_notifier_seq != mmu_seq;
+	return kvm->mmu_invalidate_seq != mmu_seq;
 }
 
 static kvm_pfn_t hva_to_pfn_retry(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
@@ -155,7 +156,7 @@ static kvm_pfn_t hva_to_pfn_retry(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
 	gpc->valid = false;
 
 	do {
-		mmu_seq = kvm->mmu_notifier_seq;
+		mmu_seq = kvm->mmu_invalidate_seq;
 		smp_rmb();
 
 		write_unlock_irq(&gpc->lock);